Daniel Geiger

[FEATURE] Checkpointing

3

Hello, I was confused to see that the default training pipeline does not save state_dicts at lowest validation loss? Also I am curious why there is no validation splitting? There...

[BUG] semantic error in learning objective loss function

5

I think there is a sematic error in the learning objective loss function. in the train_seg function, at the part where you would compute mse between predicted flows and Gt...